Laser & Optoelectronics Progress, Volume. 56, Issue 24, 241501(2019)
Extraction Method of Interest Text in Image Based on Recurrent Neural Network
Fig. 1. Example of name entity recognition
Fig. 2. LSTM network unit
Fig. 3. Structure of forward long short time memory network
Fig. 4. Structure of BLSTM network
Fig. 5. Structure of CRF network
Fig. 6. Structure of BLSTM-CRFs model
Fig. 7. Samples of text data and label generated in IDTRAIN and IDVAL. (a) Sample a; (b) sample b
Fig. 8. Samples of images in YNIDREAL
Fig. 9. Accuracy of six entities on IDVAL. (a)
Fig. 10. Test results on YNIDREAL dataset. (a) Text detection results; (b) text recognition results; (c) result of interest text extraction using BLSTM-CRF model; (d) result of interest text extraction using CRF model
|
|
|
Get Citation
Copy Citation Text
Hengjie Yang, Zheng Yan, Zongling Wu, Dingbang Fang, Fang Duan. Extraction Method of Interest Text in Image Based on Recurrent Neural Network[J]. Laser & Optoelectronics Progress, 2019, 56(24): 241501
Category: Machine Vision
Received: May. 5, 2019
Accepted: Jun. 6, 2019
Published Online: Nov. 26, 2019
The Author Email: Duan Fang (nkfetsh@gmail.com)